7. Bill Gates, then Chairman, Microsoft
“A breakthrough in
machine learning would be
worth ten Microsofts.”
8.
9.
10.
11. Deep Learning Algos
• Deep Boltzmann Machine (DBM)
• Deep Belief Networks (DBN)
• Convolutional Neural Network (CNN)
• Stacked Auto-Encoders
12. HISTORY
• Neural nets - big in the late 80’s -
Despite a commonly-held belief, there
have been numerous successful
applications
• Out of fashion in the 90’s
• 2003 renewed interest in the problem
of learning representations (as
opposed to just learning simple
classifiers) - LeChun
• 2006-2007 traction via unsupervised
training - Ng
• Now “Deep Learning” has come to
designate any learning method that
can train a system with more than 2
or 3 non-linear hidden layers.
13. WHY NOW?
• More and diverse data
• More processing power
• Algorithm advances and discoveries
• GPUs
24. TensorFlow™ is an open source software
library for numerical computation using data
flow graphs. Nodes in the graph represent
mathematical operations, while the graph
edges represent the multidimensional data
arrays (tensors) communicated between
them. The flexible architecture allows you to
deploy computation to one or more CPUs or
GPUs in a desktop, server, or mobile device
with a single API.
25. The goal of Torch is to have maximum flexibility and speed in building your
scientific algorithms while making the process extremely simple. Torch
comes with a large ecosystem of community-driven packages in machine
learning, computer vision, signal processing, parallel processing, image,
video, audio and networking among others, and builds on top of the Lua
community.
At the heart of Torch are the popular neural network and optimization
libraries which are simple to use, while having maximum flexibility in
implementing complex neural network topologies. You can build arbitrary
graphs of neural networks, and parallelize them over CPUs and GPUs in an
efficient manner.
26. • Pylearn2 is a machine learning library. Most of its functionality is built on top of Theano. It provides parallelization with
CPUs and GPUs.
• Theano — An open source machine learning library for Python.
• Deeplearning4j — An open source deep learning library written for Java. It provides parallelization with CPUs and
GPUs.
• OpenNN — An open source C++ library which implements deep neural networks and provides parallelization with
CPUs.
• NVIDIA cuDNN — A GPU-accelerated library of primitives for deep neural networks.
• DeepLearnToolbox — A Matlab/Octave toolbox for deep learning.
• convnetjs — A Javascript library for training deep learning models. It contains online demos.
• Gensim — A toolkit for natural language processing implemented in the Python programming language.
• Caffe — A deep learning framework.
• Apache SINGA — A deep learning platform developed for scalability, usability and extensibility.
• RNNLM — RNN language model open source.
• RNNLMPara — Parallel RNN language model trainer open source.
Other Tools
27. Karl Seiler | President
karl@piviting.com
Piviting.com
@pivitguru
SMARTER CHANGE